Python wbdc data annalysis ensemble methods¶
In [1]:
import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
%matplotlib inline
In [2]:
pwd
Out[2]:
In [3]:
df = pd.read_csv("wbcd.csv")
In [4]:
df.head()
Out[4]:
In [5]:
df.keys()
Out[5]:
In [7]:
df.describecribecribe()
Out[7]:
In [6]:
sns.pairplot(df,hue='diagnosis',palette='Set1')
Out[6]:
Train test Split¶
In [9]:
X = df.drop('diagnosis',axis=1)
y = df['diagnosis']
In [10]:
from sklearn.model_selection import train_test_split
In [11]:
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.30)
Bagging Classifier¶
In [12]:
from sklearn.ensemble import BaggingClassifier # imported bagging classifier algorithm
BaggingClassifier?
In [13]:
from sklearn.neighbors import KNeighborsClassifier
m = KNeighborsClassifier(n_neighbors=3)
In [14]:
# lets make a bagging classifier
bag = BaggingClassifier(
m,
max_samples=.5,
max_features=2,
n_jobs=2,
oob_score=True)
In [15]:
bag.fit(X_train, y_train) #
Out[15]:
Predictions and Evaluations of Bagging¶
In [16]:
pred = bag.predict(X_test)
In [17]:
from sklearn.metrics import classification_report,confusion_matrix
In [18]:
print(confusion_matrix(y_test,pred))
In [19]:
print(classification_report(y_test,pred))
In [20]:
bag.oob_score_
Out[20]:
In [21]:
bag.score(X, y)
Out[21]:
Descision Tree classifier¶
In [22]:
from sklearn.tree import DecisionTreeClassifier
DecisionTreeClassifier?
In [23]:
Ds = DecisionTreeClassifier()
In [24]:
Ds.fit(X,y)
Out[24]:
Predictions and Evaluations of Descision Tree classifer¶
In [25]:
pred = Ds.predict(X_test)
In [26]:
print(confusion_matrix(y_test,pred))
In [27]:
print(classification_report(y_test,pred))
In [28]:
Ds.score(X,y)
Out[28]:
Random Forests¶
In [29]:
from sklearn.ensemble import RandomForestClassifier
RandomForestClassifier?
In [30]:
Rm = RandomForestClassifier(n_estimators=20, oob_score=True)
In [31]:
Rm.fit(X, y)
Out[31]:
Predictions and Evaluations of Random classifer¶
In [32]:
pred = Rm.predict(X_test)
In [33]:
print(confusion_matrix(y_test,pred))
In [34]:
print(classification_report(y_test,pred))
In [35]:
Rm.score(X, y)
Out[35]:
AdaBoost Classifier¶
In [37]:
from sklearn.ensemble import AdaBoostClassifier
AdaBoostClassifier?
In [38]:
Ad = AdaBoostClassifier(base_estimator=None, n_estimators=100)
In [39]:
Ad.fit(X, y)
Out[39]:
Predictions and Evaluations of AdABoost classifer¶
In [40]:
pred = Ad.predict(X_test)
In [41]:
print(confusion_matrix(y_test,pred))
In [42]:
print(classification_report(y_test,pred))
In [43]:
Ad.score(X, y)
Out[43]:
Gradient Tree Boosting¶
In [44]:
from sklearn.ensemble import GradientBoostingClassifier
GradientBoostingClassifier?
In [45]:
Gb = GradientBoostingClassifier(n_estimators=10)
Gb.fit(X, y)
Gb.score(X, y)
Out[45]:
Predictions and Evaluations of Gradient Tree Boosting¶
In [46]:
pred = Gb.predict(X_test)
In [47]:
print(confusion_matrix(y_test,pred))
In [48]:
print(classification_report(y_test,pred))
In [49]:
Gb.score(X, y)
Out[49]:
Voting Classifier¶
In [50]:
from sklearn.ensemble import VotingClassifier
VotingClassifier?
In [51]:
from sklearn.linear_model import LogisticRegression
from sklearn.naive_bayes import GaussianNB
from sklearn.ensemble import RandomForestClassifier
Vm = VotingClassifier(
estimators=[('lr', LogisticRegression()),
('rf', RandomForestClassifier()),
('gnb', GaussianNB())], voting='hard')
In [52]:
Vm.fit(X, y)
Out[52]:
In [53]:
Vm.score(X, y)
Out[53]:
In [ ]: